Paper Search MCP

Instructions

Implementation Reference

• paper_search_mcp/server.py:585-598 (handler)

  The MCP tool handler for 'read_iacr_paper' in server.py, which calls the underlying iacr_searcher instance.

  async def read_iacr_paper(paper_id: str, save_path: str = "./downloads") -> str:
      """Read and extract text content from an IACR ePrint paper PDF.
  
      Args:
          paper_id: IACR paper ID (e.g., '2009/101').
          save_path: Directory where the PDF is/will be saved (default: './downloads').
      Returns:
          str: The extracted text content of the paper.
      """
      try:
          return iacr_searcher.read_paper(paper_id, save_path)
      except Exception as e:
          print(f"Error reading paper {paper_id}: {e}")
          return ""

• paper_search_mcp/academic_platforms/iacr.py:223-291 (handler)

  The core implementation of the read_paper logic within the IACRSearcher class.

  def read_paper(self, paper_id: str, save_path: str = "./downloads") -> str:
      """
      Download and extract text from IACR paper PDF
  
      Args:
          paper_id: IACR paper ID
          save_path: Directory to save downloaded PDF
  
      Returns:
          str: Extracted text from the PDF or error message
      """
      try:
          # First get paper details to get the PDF URL
          paper = self.get_paper_details(paper_id)
          if not paper or not paper.pdf_url:
              return f"Error: Could not find PDF URL for paper {paper_id}"
  
          # Download the PDF
          pdf_response = requests.get(paper.pdf_url, timeout=30)
          pdf_response.raise_for_status()
  
          # Create download directory if it doesn't exist
          os.makedirs(save_path, exist_ok=True)
  
          # Save the PDF
          filename = f"iacr_{paper_id.replace('/', '_')}.pdf"
          pdf_path = os.path.join(save_path, filename)
  
          with open(pdf_path, "wb") as f:
              f.write(pdf_response.content)
  
          # Extract text using PyPDF2
          reader = PdfReader(pdf_path)
          text = ""
  
          for page_num, page in enumerate(reader.pages):
              try:
                  page_text = page.extract_text()
                  if page_text:
                      text += f"\n--- Page {page_num + 1} ---\n"
                      text += page_text + "\n"
              except Exception as e:
                  logger.warning(
                      f"Failed to extract text from page {page_num + 1}: {e}"
                  )
                  continue
  
          if not text.strip():
              return (
                  f"PDF downloaded to {pdf_path}, but unable to extract readable text"
              )
  
          # Add paper metadata at the beginning
          metadata = f"Title: {paper.title}\n"
          metadata += f"Authors: {', '.join(paper.authors)}\n"
          metadata += f"Published Date: {paper.published_date}\n"
          metadata += f"URL: {paper.url}\n"
          metadata += f"PDF downloaded to: {pdf_path}\n"
          metadata += "=" * 80 + "\n\n"
  
          return metadata + text.strip()
  
      except requests.RequestException as e:
          logger.error(f"Error downloading PDF: {e}")
          return f"Error downloading PDF: {e}"
      except Exception as e:
          logger.error(f"Read paper error: {e}")
          return f"Error reading paper: {e}"

• paper_search_mcp/server.py:584-585 (registration)

  Tool registration decorator for read_iacr_paper.

  @mcp.tool()
  async def read_iacr_paper(paper_id: str, save_path: str = "./downloads") -> str: